Benchmark
Dtbench EDT answer preference
Coding benchmarks compare models on programming tasks. Scores are percentages.
All coding benchmarksScores from Epoch AI Benchmarking Hub data.
- Models measured
- 170
- Scores recorded
- 177
- Sources
- 1
- IQ weight
- 0.99
Score distribution
- 67.8%
- Mean
- 69%
- Median
- 11.3%
- Std dev
- 53%
- 10th percentile
- 81.6%
- 90th percentile
- 43.3%
- Min
This benchmark has a weight of 0.99 for chat models, measured over 170 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
Showing 101–150 of 177 results.
Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence)